paper-with-me

Image Captioning 벤치마크

Image Captioning on Flickr30k Captions test

7개 결과 · ⬇ CSV · JSON

BLEU-4

15.7 19.3 22.9 26.5 30.1 2014-12 2026-09 BRNN — 15.7 (2014-12-07) Cornia et al — 21.3 (2017-06-26) Unified VLP — 30.1 (2019-09-24) BRNN — 15.7 (2014-12-07) Cornia et al — 21.3 (2017-06-26) Unified VLP — 30.1 (2019-09-24)
RankModel BLEU-4CIDErMETEORSPICE Extra Training Data PaperCodeYear
1 Unified VLP 30.167.42317 Unified Vision-Language Pre-Training for Image Captioning and VQA rmokady/clip_prefix_caption · LuoweiZhou/VLP · WebQnA/WebQA_Baseline 2019
2 Cornia et al 21.346.420.0- Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention 2017
3 BRNN 15.724.715.3- Deep Visual-Semantic Alignments for Generating Image Descriptions VinitSR7/Image-Caption-Generation · Lieberk/Paddle-AoA-Captioning · souvikshanku/digit-captioning · +1 2014
4 KOSMOS-1 1.6B (zero-shot) 67.114.5
5 MetaLM 43.311.7 Language Models are General-Purpose Interfaces microsoft/unilm 2022
6 FewVLM 31.010.0 A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models woojeongjin/fewvlm 2021
7 VL-T5 2.62.0 Unifying Vision-and-Language Tasks via Text Generation j-min/VL-T5 · mitvis/vistext 2021
1–7 / 7 페이지당 10 20 50 100